Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 6, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.0K

Transforming tabular data into images for deep learning models.

Abdullah Elen1, Emre Avuçlu2

  • 1Department of Software Engineering, Faculty of Engineering and Naturel Sciences, Bandirma Onyedi Eylul University, Bandirma, Balikesir, Turkiye.

Neural Networks : the Official Journal of the International Neural Network Society
|February 15, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Transformations of Functions III01:20

Transformations of Functions III

304
Transformations modify the graphical representation of a function without changing its fundamental form. One common transformation is reflection, which flips the graph across a designated axis. When the vertical coordinates of all points are multiplied by the negative one, the entire graph is mirrored over the horizontal axis. This transformation reverses the vertical orientation of peaks and troughs, akin to signal inversion in electrical systems, where a waveform is flipped, but the timing of...
304

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Fast and Accurate Classification of Corn Varieties Using Deep Learning With Edge Detection Techniques.

Journal of food science·2025
Same author

Covid-19 detection from radiographs by feature-reinforced ensemble learning.

Concurrency and computation : practice & experience·2022
Same author

COVID-19 detection using X-ray images and statistical measurements.

Measurement : journal of the International Measurement Confederation·2022
Same author

A novel method using Covid-19 dataset and machine learning algorithms FOR THE MOST ACCURATE DIAGNOSIS that can be obtained in medical diagnosis.

Biomedical signal processing and control·2022
Same author

Evaluation of train and test performance of machine learning algorithms and Parkinson diagnosis with statistical measurements.

Medical & biological engineering & computing·2020
Same author

Learn from one data set to classify all - A multi-target domain adaptation approach for white blood cell classification.

Computer methods and programs in biomedicine·2020
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

New results on prescribed-time synchronization of complex networks via intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Variance-constrained multi-view ensemble broad network for imbalanced data.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces a new method to convert numerical tabular data into images, allowing deep learning models to analyze it effectively. This image-based deep learning approach significantly improves classification accuracy on diverse datasets.

Area of Science:

  • Computer Science
  • Machine Learning
  • Data Science

Background:

  • Deep learning (DL) excels with unstructured data (images, text) but struggles with tabular numerical data due to its lack of spatial structure.
  • Traditional machine learning methods often fall short on complex numerical datasets.
  • Bridging the gap between DL and numerical data analysis is crucial for broader AI applications.

Purpose of the Study:

  • To develop a novel method for transforming numerical tabular data into grayscale image representations.
  • To enable the application of deep learning architectures, such as Convolutional Neural Networks (CNNs), to numerical datasets.
  • To enhance the performance and applicability of deep learning in analyzing structured numerical information.

Main Methods:

  • Numerical features are normalized and organized into square image matrices.
Keywords:
Deep learningImage classificationMachine learningNumerical data transformationTabular dataset

Related Experiment Videos

Last Updated: May 6, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.0K
  • Labeled grayscale images are generated from the transformed tabular data.
  • Experiments utilize Residual Network (ResNet-18) and Directed Acyclic Graph Neural Network (DAG-Net) models with 5-fold cross-validation on four public datasets (RMSCD, Optdigits, TUNADROMD, Spambase).

    • Main Results:

    • The Directed Acyclic Graph Neural Network (DAG-Net) achieved high accuracies: 99.91% (RMSCD), 99.77% (Optdigits), 98.84% (TUNADROMD), and 93.06% (Spambase).
    • Ablation studies and efficiency analyses confirmed improvements in training performance and reduced computational costs.
    • The image-based transformation proved effective for classification tasks on numerical datasets.

    Conclusions:

    • The proposed image transformation method offers a practical and efficient strategy for integrating numerical datasets into deep learning workflows.
    • This approach broadens the applicability of deep learning techniques across diverse domains previously challenging for DL.
    • The open-source release of the implementation facilitates reproducibility and encourages further research in this area.